Variational (untied weights, MC) LSTM (Large)
University of CambridgeLanguage modeling
Variational (untied weights, MC) LSTM (Large) is language modeling model published by University of Cambridge in 2015 featuring 66000000.0 parameters.
About Variational (untied weights, MC) LSTM (Large)
Recurrent neural networks (RNNs) stand at the forefront of many recent developments in deep learning. Yet a major difficulty with these models is their tendency to overfit, with dropout shown to fail when applied to recurrent layers. Recent results a
Details
- Provider
- University of Cambridge
- Task
- Language modeling
- Parameters
- 66000000.0
- Released
- 2015-12-16
- Open weights
- No